ReconPhys is the first feedforward neural network that jointly reconstructs 3D geometry and appearance via Gaussian Splatting while estimating physical attributes from a single monocular video using self-supervised training.
Embodiedreamer: Advancing real2sim2real transfer for policy training via embodied world modeling
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CV 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
A video transfer pipeline augments simulated VLA data into realistic videos while preserving actions, yielding consistent performance gains on robot benchmarks such as 8% on Robotwin 2.0.
SFI-Bench shows current multimodal LLMs struggle to integrate spatial memory with functional reasoning and external knowledge in video tasks.
citing papers explorer
-
ReconPhys: Reconstruct Appearance and Physical Attributes from Single Video
ReconPhys is the first feedforward neural network that jointly reconstructs 3D geometry and appearance via Gaussian Splatting while estimating physical attributes from a single monocular video using self-supervised training.
-
Seeing Realism from Simulation: Efficient Video Transfer for Vision-Language-Action Data Augmentation
A video transfer pipeline augments simulated VLA data into realistic videos while preserving actions, yielding consistent performance gains on robot benchmarks such as 8% on Robotwin 2.0.
-
From Where Things Are to What They Are For: Benchmarking Spatial-Functional Intelligence in Multimodal LLMs
SFI-Bench shows current multimodal LLMs struggle to integrate spatial memory with functional reasoning and external knowledge in video tasks.